Train mem usage and other improvements

common/common.cpp

@@ -15,6 +15,7 @@
 #include <string>
 #include <unordered_set>
 #include <vector>
+#include <cinttypes>
 
 #if defined(__APPLE__) && defined(__MACH__)
 #include <sys/types.h>
@@ -938,8 +939,8 @@ std::string get_sortable_timestamp() {
 
     const int64_t ns = std::chrono::duration_cast<std::chrono::nanoseconds>(
         current_time.time_since_epoch() % 1000000000).count();
-    char timestamp_ns[10];
-    snprintf(timestamp_ns, 11, "%09ld", ns);
+    char timestamp_ns[11];
+    snprintf(timestamp_ns, 11, "%09" PRId64, ns);
 
     return std::string(timestamp_no_ns) + "." + std::string(timestamp_ns);
 }

examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp

@@ -681,7 +681,6 @@ void save_as_llama_model(struct llama_vocab * vocab, struct my_llama_model * mod
 
     // for rms-att-weight
     int row_length = model->hparams.n_embd;
-    const auto & hparams = model->hparams;
     int n_ff = model->hparams.n_ff;
 
     for (uint32_t i = 0; i < model->hparams.n_layer; ++i){

examples/gguf/CMakeLists.txt

@@ -0,0 +1,5 @@
+set(TARGET gguf)
+add_executable(${TARGET} gguf.cpp)
+install(TARGETS ${TARGET} RUNTIME)
+target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)

examples/train-text-from-scratch/README.md

@@ -8,15 +8,15 @@ wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/s
 
 # train
 ./bin/train-text-from-scratch \
-        --vocab-model ../models/ggml-vocab.bin \
+        --vocab-model ../models/ggml-vocab-llama.gguf \
         --ctx 64 --embd 256 --head 8 --layer 16 \
-        --checkpoint-in  chk-shakespeare-256x16.bin \
-        --checkpoint-out chk-shakespeare-256x16.bin \
-        --model-out ggml-shakespeare-256x16-f32.bin \
+        --checkpoint-in  chk-shakespeare-256x16.gguf \
+        --checkpoint-out chk-shakespeare-256x16.gguf \
+        --model-out ggml-shakespeare-256x16-f32.gguf \
         --train-data "shakespeare.txt" \
-        -t 6 -b 16 -n 32 --seed 1 --adam-iter 16 \
-        --print-details-interval 0 --predict 16 --use-flash
+        -t 6 -b 16 --seed 1 --adam-iter 256 \
+        --no-checkpointing
 
 # predict
-./bin/main -m ggml-shakespeare-256x16-f32.bin
+./bin/main -m ggml-shakespeare-256x16-f32.gguf
 ```